feature-forge
Conducts structured requirements workshops to produce feature specifications, user stories, EARS-format functional requirements, acceptance criteria, and implementation checklists. Use when defining new features, gathering requirements, or writing specifications. Invoke for feature definition, requirements gathering, user stories, EARS format specs, PRDs, acceptance criteria, or requirement matrices.
90
78%
Does it follow best practices?
Impact
98%
1.84xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/feature-forge/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates specific deliverables, provides explicit trigger guidance with both 'Use when' and 'Invoke for' clauses, and covers a comprehensive set of natural keywords users would employ. The description is well-structured, uses third person voice correctly, and occupies a distinct niche in requirements engineering that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'structured requirements workshops', 'feature specifications', 'user stories', 'EARS-format functional requirements', 'acceptance criteria', and 'implementation checklists'. These are all concrete, named deliverables. | 3 / 3 |
Completeness | Clearly answers both 'what' (conducts structured requirements workshops to produce feature specifications, user stories, EARS-format functional requirements, acceptance criteria, and implementation checklists) and 'when' (explicit 'Use when' and 'Invoke for' clauses with specific trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'feature definition', 'requirements gathering', 'user stories', 'EARS format specs', 'PRDs', 'acceptance criteria', 'requirement matrices', 'specifications'. These cover a wide range of how users naturally phrase requirements-related requests. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around requirements engineering and feature specification. The mention of EARS-format, requirements workshops, PRDs, and requirement matrices makes it highly distinctive and unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill demonstrates strong progressive disclosure with a well-organized reference table and reasonable structure. However, it falls short on actionability—the workflow steps describe actions at a high level without showing concrete tool usage patterns or complete examples. The workflow would benefit from explicit feedback loops, particularly between the Validate and Interview steps.
Suggestions
Add a concrete example of an `AskUserQuestions` tool invocation showing structured choices (e.g., priority selection) to make the actionability more copy-paste ready.
Add explicit feedback loops in the workflow: e.g., 'If validation reveals gaps or ambiguities, return to step 2 (Interview) to resolve them before finalizing the spec.'
Remove or condense the 'When to Use This Skill' section since it duplicates the skill description and consumes tokens without adding value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary framing (e.g., 'When to Use This Skill' largely repeats what the skill description already conveys, and the Role Definition section explains PM/Dev perspectives that Claude can infer). The constraints section has some redundancy with the workflow. | 2 / 3 |
Actionability | Provides a clear workflow and references to external files, but the core skill itself lacks fully concrete, executable guidance—it describes what to do at each step rather than showing exact tool invocations, specific question templates inline, or complete output examples. The EARS and acceptance criteria examples are helpful but minimal. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and logically ordered, but lacks explicit validation checkpoints or feedback loops between steps. There's no guidance on what to do if the validation step (step 4) reveals gaps—no explicit 'loop back to Interview' instruction. For a requirements process where errors compound, this is a meaningful gap. | 2 / 3 |
Progressive Disclosure | Excellent use of a reference table with clear 'Load When' conditions, keeping the main skill lean while pointing to one-level-deep references for EARS syntax, interview questions, specification template, acceptance criteria, and pre-discovery subagents. Navigation is clear and well-signaled. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jeffallan/claude-skills
- Commit
3d95bb1
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.